recent_changes · Mcp Semanticscholar MCP: Risk & Policy

WHAT IT DOES

What recent_changes does on Mcp Semanticscholar

AI agents call recent_changes to retrieve information from Mcp Semanticscholar without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

PARAMETERS

Parameter	Type	Required	Description
`type`	string	Yes	Entity type. Only "company" supported today.
`since`	string	Yes	Window start — ISO date ("2026-04-01") or relative ("7d", "30d", "3m", "1y"). Use "30d" or "1m" for typical monitoring.
`value`	string	Yes	Ticker (e.g., "AAPL") or zero-padded CIK (e.g., "0000320193").

Parameters from the server's own tool schema.

WHY IT NEEDS A POLICY

Why recent_changes needs a policy

This is a Read tool because it exclusively retrieves, aggregates, and queries publicly available data from SEC filings, news feeds, and patent records. It has no side effects—it does not create, modify, delete, or execute code. The blast radius of misuse is minimal; an AI agent querying this tool repeatedly or with spam company names might cause rate-limiting but cannot corrupt data or trigger financial transactions.

From the tool's definition The tool retrieves and queries data from multiple sources (SEC EDGAR filings, GDELT/GNews news mentions, USPTO patents). The description explicitly indicates it 'returns structured' data and performs lookups across public databases.

Attacks that exploit this kind of access

Questions about recent_changes

What does the recent_changes tool do? +

"What's new with X" / "latest on Y" / "what happened to Z this week / month / quarter" / "updates on Acme" / "news on Tesla recently" / "what's happening with Apple" — change feed for a company in the last N days/weeks/months in ONE parallel call. Fans out to SEC EDGAR (filings since since), GDELT→GNews fallback (news mentions in window — GDELT preferred, GNews when rate-limited or 5xx), USPTO (patents granted; PatentsView API sunset May 2025 so this soft-fails until reactivated). since accepts ISO date ("2026-04-01") or relative shorthand ("7d", "30d", "3m", "1y"). Returns structured changes[] grouped by source + total_changes count + pipeworx:// citation URIs. Use entity_profile instead when you want the static profile (filings + fundamentals + LEI + patents) regardless of window. It is categorised as a Read tool in the Mcp Semanticscholar MCP Server, which means it retrieves data without modifying state.

What parameters does recent_changes accept? +

recent_changes accepts 3 parameters: type, since, value. Required: type, since, value. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on recent_changes? +

Register the Mcp Semanticscholar MCP server in PolicyLayer and add a rule for recent_changes: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Semanticscholar. Nothing to install.

What risk level is recent_changes? +

recent_changes is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit recent_changes? +

Yes. Add a rate_limit block to the recent_changes rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block recent_changes completely? +

Set action: deny in the PolicyLayer policy for recent_changes. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides recent_changes? +

recent_changes is provided by the Mcp Semanticscholar MCP server (https://gateway.pipeworx.io/semanticscholar/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.